Today's AI systems are extraordinarily capable engineers but lack tasteful, original creativity — they fail to produce research of top ML conference caliber because they commit to narrow research paths early and cannot reverse out of unpromising approaches.

A shadow-evaluation study giving frontier agents unpublished NeurIPS 2026 research questions found both papers rejected for no novel contribution, poorly motivated experiments, and impenetrable prose, suggesting AI agents lack the creative insight needed to move the field forward. ✦ AI generated

Authors of the shadow-evaluation study (Princeton, Cornflower Labs, UK AI Security Institute, et al.) · Import AI · 2026-08-03 · original ↗

While agents could solve the engineering problems necessary to do the research, they failed to produce original research at the caliber of a top ML conference. ... The [human] authors rejected both papers. The Personas paper was scored a 2 ("Reject"), and the TabPFN paper was scored a 1 ("Strong Reject"). Both reviews highlighted the same failures: poorly motivated data and experiments, no novel contribution, and impenetrable prose.

Read full article ↗excerpt · fair-use quotation